Model Architecture

Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity ICLR 2025 Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions ICML 2025 Training-and-Prompt-Free General Painterly Harmonization via Zero-Shot Disentenglement on Style and Content References AAAI 2025 Training-free and Adaptive Sparse Attention for Efficient Long Video Generation ICCV 2025 Training-Free Message Passing for Learning on Hypergraphs ICLR 2025 Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weights CVPR 2025 Training Neural Networks as Recognizers of Formal Languages ICLR 2025 Training Verification-Friendly Neural Networks via Neuron Behavior Consistency AAAI 2025 Training with Confidence: Catching Silent Errors in Deep Learning Training with Automated Proactive Checks OSDI 2025 Transformed Low-rank Adaptation via Tensor Decomposition and Its Applications to Text-to-image Models ICCV 2025 Transformer Meets Twicing: Harnessing Unattended Residual Information ICLR 2025 Transformers Learn Low Sensitivity Functions: Investigations and Implications ICLR 2025 Transformers without Normalization CVPR 2025 TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training ICCV 2025 Trusted Multi-View Classification via Evolutionary Multi-View Fusion ICLR 2025 TrustMark: Robust Watermarking and Watermark Removal for Arbitrary Resolution Images ICCV 2025 TtBA: Two-third Bridge Approach for Decision-Based Adversarial Attack ICML 2025 T-T: Table Transformer for Tagging-based Aspect Sentiment Triplet Extraction IJCAI 2025 TULIP: Token-length Upgraded CLIP ICLR 2025 Tuning Frequency Bias of State Space Models ICLR 2025 Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization ICLR 2025 Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse Factorization ICLR 2025 u-μP: The Unit-Scaled Maximal Update Parametrization ICLR 2025 Uncover Treasures in DCT: Advancing JPEG Quality Enhancement by Exploiting Latent Correlations ICCV 2025 UniConvNet: Expanding Effective Receptive Field while Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale ICCV 2025